What are .dx exactly? about deeppocket HOT 8 OPEN

by threshold I mean the "-t" argument, this specifies the confidence level on whether the model considers a voxel point to be a part of the binding site or not. If the model does not predict any points with confidence greater than "t" you will not get any segmented shapes for that pocket.

from deeppocket.

yes thats right

from deeppocket.

I have looked at several examples, and they all look like this. That cube has only one or two dots. I did not edit the code, and this is what I got.

1a9w_E.clean_nowat_1.txt
1a52_A.clean_nowat_1.txt
1aii_A.clean_nowat_1.txt

from deeppocket.

the .dx files are supposed to be predicted outputs from the segmentation model put in that format for visualization. Sometimes the model doesn't like the pocket provided to it and so it predicts very little, if this is a persisting problem then it is worrisome. Just for debugging purposes, could you use a lower threshold and see if you get a larger set of points?

from deeppocket.

in any case, even if the segmentation model doesn't like the pocket, the classification model still ranks the fpocket output. So you could use the reranked fpocket predictions if that serves your purpose

from deeppocket.

@RishalAggarwal, by lower threshold, do you mean a higher distance? >3.5? Is there an email address where I can reach you? I have another query I would like to discuss! Thanks!

from deeppocket.

The .dx issue is actually for ALL pockets. Those segmented out, and those that are not.

from deeppocket.

I see, but then the confidence of the segmented pockets would be lower, right?

from deeppocket.